def processMedia(objectId, tweet):
'''Handles the formatting of the tweet media to be compatible with crowded.'''
try:
entities = tweet['entities']
except:
logging.error("Failed to get entities field from tweet. Tweet: \n%s" %
(tweet),
exc_info=True)
return None
#Get the media
thumbUrl, lowUrl, stdUrl = getMedia(entities['media'])
# Get the tags
if entities.has_key('hashtags'):
hashtags = getTags(entities['hashtags'])
# Get the tweet
try:
caption = decodeEncode(tweet['text'])
except:
logging.debug("Failed to parse caption: %s" % (tweet['text']),
exc_info=True)
caption = '***caption not parsed***'
# Get the datetime out as ISO
dt = getDatetime(tweet)
# Kludge them together
mediaTweet = {
'standard_resolution': stdUrl,
'low_resolution': lowUrl,
'thumbnail': thumbUrl,
'dt': dt,
'source': 'twitter',
'caption': caption,
'tags': hashtags,
'objectId': str(objectId)
}
tweetOut = {'data': [mediaTweet]}
return tweetOut
def processMedia(objectId, tweet):
"""Handles the formatting of the tweet media to be compatible with crowded."""
try:
entities = tweet["entities"]
except:
logging.error("Failed to get entities field from tweet. Tweet: \n%s" % (tweet), exc_info=True)
return None
# Get the media
thumbUrl, lowUrl, stdUrl = getMedia(entities["media"])
# Get the tags
if entities.has_key("hashtags"):
hashtags = getTags(entities["hashtags"])
# Get the tweet
try:
caption = decodeEncode(tweet["text"])
except:
logging.debug("Failed to parse caption: %s" % (tweet["text"]), exc_info=True)
caption = "***caption not parsed***"
# Get the datetime out as ISO
dt = getDatetime(tweet)
# Kludge them together
mediaTweet = {
"standard_resolution": stdUrl,
"low_resolution": lowUrl,
"thumbnail": thumbUrl,
"dt": dt,
"source": "twitter",
"caption": caption,
"tags": hashtags,
"objectId": str(objectId),
}
tweetOut = {"data": [mediaTweet]}
return tweetOut
handleErrors(p, e)
i = 1
for line in f:
# Tidy up before dealing with the words
try:
line = line.rstrip('\n').rstrip('\r')
line = line.split(',')
word, pho = line[0], line[1]
except Exception, e:
handleErrors(p, e)
word = decodeEncode(word.lower())
pho = decodeEncode(pho.lower())
# Pass to mongo inserter
res = mongoInserter(p, collection, word, pho)
# Counter
i += 1
if p.verbose == True and i % 1000 == 0:
print i
f.close()
mdb.close(c, dbh)
#----------------------------------------------------------------------------------------
print e
handleErrors(p, e)
i = 1
for line in f:
# Tidy up before dealing with the words
try:
line = line.rstrip("\n").rstrip("\r")
line = line.split(",")
slang, word = line[0], line[1]
except Exception, e:
handleErrors(p, e)
word = decodeEncode(word.lower())
slang = decodeEncode(slang.lower())
# Pass to mongo inserter
res = mongoUpdate(p, collection, word, slang)
# Counter
i += 1
if p.verbose == True and i % 100 == 0:
print i
f.close()
mdb.close(c, dbh)
# ----------------------------------------------------------------------------------------
# Tidy up before dealing with the words
try:
line = line.rstrip('\n').rstrip('\r')
line = line.lstrip(',').rstrip(',')
line = line.split(',')
except Exception, e:
handleErrors(p, e)
# Split up the line and take the first 2 columns
try:
word, token = line[0], line[1]
except Exception, e:
handleErrors(p, "\nLine:\n%s\n\n" %line)
# Handle the decoding/encoding for mongo
word = decodeEncode(word.lower())
token = decodeEncode(token)
# Drop the lead and end spaces and make it a list
token = token.strip()
# Get the space-removed emoticons
tokens = getDespaced(token)
tokens += getDespaced(token.lower())
# Pass to mongo inserter
for token in tokens:
res = mongoUpdate(p, emoCollection, word, token)
# Counter
i += 1
